Statistical Relational Learning to Recognise Textual Entailment

We propose a novel approach to recognise textual entailment RTE following a two-stage architecture --- alignment and decision --- where both stages are based on semantic representations. In the alignment stage the entailment candidate pairs are represented and aligned using predicate-argument structures. In the decision stage, a Markov Logic Network MLN is learnt using rich relational information from the alignment stage to predict an entailment decision. We evaluate this approach using the RTE Challenge datasets. It achieves the best results for the RTE-3 dataset and shows comparable performance against the state of the art approaches for other datasets.

[1]  Ido Dagan,et al.  A Lexical Alignment Model for Probabilistic Textual Entailment , 2005, MLCW.

[2]  Ben Taskar,et al.  Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning) , 2007 .

[3]  Johanna D. Moore,et al.  36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, COLING-ACL '98, August 10-14, 1998, Université de Montréal, Montréal, Quebec, Canada. Proceedings of the Conference. , 1998 .

[4]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[5]  Christopher D. Manning,et al.  Learning to distinguish valid textual entailments , 2006 .

[6]  Christopher D. Manning,et al.  A Phrase-Based Alignment Model for Natural Language Inference , 2008, EMNLP.

[7]  Katrin Erk,et al.  Integrating Logical Representations with Probabilistic Information using Markov Logic , 2011, IWCS.

[8]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[9]  Ido Dagan,et al.  Directional distributional similarity for lexical inference , 2010, Natural Language Engineering.

[10]  Kentaro Inui,et al.  Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing , 2007, ACL 2007.

[11]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[12]  Eric Yeh,et al.  Learning Alignments and Leveraging Natural Logic , 2007, ACL-PASCAL@ACL.

[13]  Christopher D. Manning,et al.  Learning to recognize features of valid textual entailments , 2006, NAACL.

[14]  Christopher D. Manning,et al.  Probabilistic Tree-Edit Models with Structured Latent Variables for Textual Entailment and Question Answering , 2010, COLING.

[15]  Lucia Specia,et al.  UOW: Semantically Informed Text Similarity , 2012, SemEval@NAACL-HLT.

[16]  Peter Clark,et al.  The Seventh PASCAL Recognizing Textual Entailment Challenge , 2011, TAC.

[17]  Patrick Pantel,et al.  VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations , 2004, EMNLP.

[18]  Lucia Specia,et al.  TINE: A Metric to Assess MT Adequacy , 2011, WMT@EMNLP.

[19]  Dekang Lin,et al.  Automatic Retrieval and Clustering of Similar Words , 1998, ACL.

[20]  Matthew Richardson,et al.  Markov logic networks , 2006, Machine Learning.

[21]  Cuong Chau,et al.  Montague Meets Markov: Deep Semantics with Probabilistic Logical Form , 2013, *SEMEVAL.

[22]  Roy Bar-Haim,et al.  The Second PASCAL Recognising Textual Entailment Challenge , 2006 .

[23]  Ion Androutsopoulos,et al.  A Survey of Paraphrasing and Textual Entailment Methods , 2009, J. Artif. Intell. Res..

[24]  Stefan Harmeling.  An Extensible Probabilistic Transformation-based Approach to the Third Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[25]  Elena Cabrio,et al.  Recognizing Textual Entailment for Italian EDITS @ EVALITA 2009 , 2009 .

[26]  Cordelia Schmid,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[27]  Christopher D. Manning,et al.  Natural Logic for Textual Inference , 2007, ACL-PASCAL@ACL.